mcpbeat Sign in

Memory.fit MCP Server

by memory Your server? Claim it
answering

Memory.fit is answering right now. Last checked 12 min ago. Last commit 27 Oct 2026.

Your training, sleep, recovery and fuel for the AI you use: it reads your week and plans the next.

Uptime history 12 days of history
12 days agonow
100.0%
Uptime 24h
91 of 91 checks
—
Tools
hidden behind auth
108 ms
Response time
average over 24h
0
Stars
last commit 27 Oct 2026

Nothing serious here today

Today is the operative word: we check Memory.fit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.

run in your terminal
claude mcp add memory-fit --transport http https://api.memory.fit/mcp
Settings → Connectors → Add custom connector, then paste this address
https://api.memory.fit/mcp
~/.codex/config.toml
[mcp_servers.memory-fit]
url = "https://api.memory.fit/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "memory-fit": {
      "url": "https://api.memory.fit/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "memory-fit": {
      "type": "http",
      "url": "https://api.memory.fit/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.

Endpoints

URLTransportStateLatencyChecked
https://api.memory.fit/mcp streamable-http sign-in 123 ms 12 min ago

Alternatives to Memory.fit

same job, measured the same way
Metodix — training log for coaches
by metodix

Training log for coaches: your AI assistant finds clients, reads history, logs and plans workouts.

answering
Geistra
by geistra

Shared memory for your AI apps: Spaces of records, files and plans you and others can work in.

answering
Ourpr MCP Server
by joeyaflores

Read your own ourpr running history in an AI agent, and put a plan on the week ahead.

58 installs/wk local only
Coach Icarus
by simkessy

Adaptive running coach MCP server — training data, plans, and recovery for AI assistants.

answering
Tally Workout
by westvegh

iPhone strength log. Any MCP agent reads your training and plans workouts in the Tally app.

answering
Reef
by reefwith

Shared, living memory for you and your people — coves your AI assistant can read and write.

answering
Garmin MCP
by garminmcp

Read-only Garmin data for your AI: sleep, Body Battery, activities, laps, and training status.

1 tools answering
WHOOP
by mcp-dir

Your WHOOP data in the assistant, read-only: recovery, sleep, strain, workouts, cycles and body meas

13 tools answering

Memory.fit — questions

Answers built from our own checks of this server.

Why is there no tool list for Memory.fit?
The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.
Is Memory.fit working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 108 ms. The bar chart above shows every period we have measured.
How do I connect Memory.fit?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to Memory.fit?
No API key is involved. Memory.fit answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is Memory.fit?
It answers our handshake in 108 ms on average, which is faster than 91% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Memory.fit open source?
The code is open source: it is published under the MIT licence and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at api.memory.fit, which runs on its operator's own terms.